陈志刚,张志昊,王衍学,等. 基于HyperMAML的小样本轴承故障诊断[J].河南理工大学学报(自然科学版)，DOI: 10.16186/j.cnki.1673-9787.2024120023

CHEN Z G,ZHANG Z H,WANG Y X,et al．Few-Shot Bearing Fault Diagnosis Based on HyperMAML［J］.Journal of Henan Polytechnic University( Natural Science)，DOI: 10.16186/j.cnki.1673-9787.2024120023

基于HyperMAML的小样本轴承故障诊断(网络首发)

陈志刚，张志昊，王衍学，刘家乐

（北京建筑大学 机电与车辆工程学院,北京 100044）

摘要: 目的 针对滚动轴承在小样本情况下为保证诊断精度导致诊断时间长、无法有效提取故障特征导致准确率低的问题，提出了一种融合超网络(hypernetworks)的模型不可知论元学习(Model-Agnostic Meta-Learning, MAML)的故障诊断方法HyperMAML。方法 首先,为了更全面的显示时间序列中的时间信息和故障特征，通过格拉姆角和场(GASF)将时间序列转变成二维灰度图；其次，利用超网络生成的权重对MAML中的权重进行更新，避免了MAML在单轮迭代中进行多次梯度更新的冗余操作，从而减少了训练时间；最后,使用更新权重后的MAML对数据集进行故障诊断。结果 公开数据集和自制试验台数据集的分析结果表明，在公开数据集上HyperMAML准确率为96.62%，训练和测试时间分别为1.221s和1.346s；MAML准确率为91.06%，训练和测试时间分别为11.313s和6.007s；RelationNet准确率为92.18%，训练和测试时间为1.644s和1.559s;ProtoNet准确率为95.08%，训练和测试时间为1.646s和1.422s；DCA-BiGRU准确率为95.34%，训练和测试时间为1.021s和0.940s。在自制试验台数据集上HyperMAML准确率为97.89%，训练和测试时间为0.851s和0.824s；MAML准确率为97.89%，训练和测试时间为6.04s和2.603s；RelationNet准确率为98.00%，训练和测试时间为0.847s和0.896s;ProtoNet准确率为97.75%，训练和测试时间为1.032s和0.875s；DCA-BiGRU准确率为97.80%，训练和测试时间为0.744s和0.692s。结论 基于HyperMAML的小样本故障诊断模型充分利用了超网络生成动态权重的能力和MAML的元学习框架优势，能够适应小样本学习条件下的故障提取特征需求，在提高模型训练效率和诊断速度的同时确保了诊断的准确率和稳定性，为小样本学习条件下的智能故障诊断提供了一种创新的解决方案。

关键词:故障诊断；滚动轴承；小样本学习；元学习；格拉姆角场

DOI: 10.16186/j.cnki.1673-9787.2024120023

基金项目:国家自然科学基金项目(52275079)，北京建筑大学研究生创新项目(PG2024134)

收稿日期：2024-12-23

修回日期：2025-06-07

网络首发日期：2025-07-30

Few-shot bearing fault diagnosis based on HyperMAML

Chen Zhigang, Zhang Zhihao, Wang Yanxue, Liu Jiale

(School of Mechanical and Vehicle Engineering, Beijing University of Civil Engineering and Architecture 100044, Beijing, China)

Abstract: Objectives To address the issues of prolonged diagnosis time caused by the need to ensure diagnostic accuracy under few-shot conditions and the low accuracy resulting from the inability to effectively extract fault features in rolling bearings, a fault diagnosis method, named HyperMAML, based on Model-Agnostic Meta-Learning (MAML) integrating hyper-networks was proposed. Methods Firstly, to more comprehensively represent the temporal information and fault features in the time series data, the time series were transformed into two-dimensional grayscale images using the Gramian Angular Summation Field (GASF). Then, the weights generated by the hypernetwork were used to update the weights in MAML, effectively avoiding the redundant gradient updates during a single iteration in MAML and thereby reducing training time. Finally, the updated MAML weights were applied to perform fault diagnosis on the dataset. Results Analysis of both public datasets and self-built test stand datasets indicated that on public datasets, HyperMAML achieved an accuracy of 96.62%, with training and testing times of 1.221s and 1.346s, respectively. MAML's accuracy was 91.06%, with training and testing times of 11.313s and 6.007s, respectively. RelationNet's accuracy was 92.18%, with training and testing times of 1.644s and 1.559s, respectively. ProtoNet's accuracy was 95.08%, with training and testing times of 1.646s and 1.422s, respectively. DCA-BiGRU's accuracy was 95.34%, with training and testing times of 1.021s and 0.940s. On the self-built test stand datasets, HyperMAML's accuracy was 97.89%, with training and testing times of 0.851s and 0.824s, respectively. MAML's accuracy was 97.89%, with training and testing times of 6.04s and 2.603s, respectively. RelationNet's accuracy was 98.00%, with training and testing times of 0.847s and 0.896s, respectively. ProtoNet's accuracy was 97.75%, with training and testing times of 1.032s and 0.875s, respectively. DCA-BiGRU's accuracy was 97.80%, with training and testing times of 0.744s and 0.692s, respectively. Conclusions The few-shot fault diagnosis model based on HyperMAML leveraged the capability of hypernetwork to generate dynamic weights and the meta-learning framework advantages of MAML. It effectively met the requirements for fault feature extraction under few-shot learning conditions, improved model training efficiency and diagnostic speed while ensuring diagnostic accuracy and stability. This model provideed an innovative solution for intelligent fault diagnosis under small-sample learning scenarios.

Key words: fault diagnosis; rolling bearings; few-shot learning; meta-learning; Gramian Angular Field